Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2704 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8655. Min Act: -0.0000

Data Index: 2875 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1587588 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1560738 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.7416. Min Act: -0.0000

Data Index: 155380 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8216. Min Act: -0.0000

Data Index: 595836 (The Pile)

Max Activating Token Index: 194

Text #5

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1738077 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6278. Min Act: -0.0000

Data Index: 75240 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6451. Min Act: -0.0000

Data Index: 388616 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5744. Min Act: -0.0000

Data Index: 874701 (The Pile)

Max Activating Token Index: 409

Text #9

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1251311 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5721. Min Act: -0.0000

Data Index: 244958 (The Pile)

Max Activating Token Index: 352

Text #11

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1275754 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5519. Min Act: -0.0000

Data Index: 406 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1016810 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1787505 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1871428 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5107. Min Act: -0.0000

Data Index: 149825 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.4735. Min Act: -0.0000

Data Index: 99828 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1689432 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1262026 (The Pile)

Max Activating Token Index: 1014